TY - GEN
T1 - Evaluating the power efficiency of deep learning inference on embedded GPU systems
AU - Rungsuptaweekoon, Kanokwan
AU - Visoottiviseth, Vasaka
AU - Takano, Ryousei
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/7/1
Y1 - 2017/7/1
N2 - Deep learning inference on embedded systems requires not only high throughput but also low power consumption. To address this challenge, this paper evaluates the power efficiency of image recognition with YOLO, a real-time object detection algorithm, on the latest NVIDIA embedded GPU systems: Jetson TX1 and TX2. For this evaluation, we deployed the Low-Power Image Recognition Challenge (LPIRC) system and integrated YOLO, a power meter, and target hardware into the system. The experimental results show that Jetson TX2 with Max-N mode has the highest throughput; Jetson TX2 with Max-Q mode has the highest power efficiency. These findings indicate it is possible to adjust the trade-off relationship of throughput and power efficiency in Jetson TX2. Therefore, Jetson TX2 has advantages for image recognition on embedded systems more than Jetson TX1 and a PC server with NVIDIA Tesla P40.
AB - Deep learning inference on embedded systems requires not only high throughput but also low power consumption. To address this challenge, this paper evaluates the power efficiency of image recognition with YOLO, a real-time object detection algorithm, on the latest NVIDIA embedded GPU systems: Jetson TX1 and TX2. For this evaluation, we deployed the Low-Power Image Recognition Challenge (LPIRC) system and integrated YOLO, a power meter, and target hardware into the system. The experimental results show that Jetson TX2 with Max-N mode has the highest throughput; Jetson TX2 with Max-Q mode has the highest power efficiency. These findings indicate it is possible to adjust the trade-off relationship of throughput and power efficiency in Jetson TX2. Therefore, Jetson TX2 has advantages for image recognition on embedded systems more than Jetson TX1 and a PC server with NVIDIA Tesla P40.
KW - deep learning
KW - embedded GPU system
KW - low-power image recognition
KW - object detection
KW - power efficiency
UR - https://www.scopus.com/pages/publications/85049446409
U2 - 10.1109/INCIT.2017.8257866
DO - 10.1109/INCIT.2017.8257866
M3 - Conference contribution
AN - SCOPUS:85049446409
T3 - Proceeding of 2017 2nd International Conference on Information Technology, INCIT 2017
SP - 1
EP - 5
BT - Proceeding of 2017 2nd International Conference on Information Technology, INCIT 2017
A2 - Sawangphol, Wudhichart
A2 - Mitrpanont, Jarernsri L.
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2nd International Conference on Information Technology, INCIT 2017
Y2 - 2 November 2017 through 3 November 2017
ER -